Preprints

  • Shiv Shankar and Ritwik Sinha and Madalina Fiterau, Combining A/A Data and LLMs for Improved Content Evaluation . In Proceedings of the Web Conference, vol. 25, 2024. pdf.
  • Sidong Zhang, Trang Nguyen, Andrea Fanelli, Shiv Shankar and Madalina Fiterau, Audio-Visual Speech Separation via Bottleneck Iterative Network. Submitted to ICASSP, 2025. pdf.
  • Shiv Shankar and Tomas Geffner. Learning Straight Flows by Learning Curved Interpolants Submited to ICML, 2025. pdf.
  • Shiv Shankar and Sidong Zhang and Trang Nguyen and Madalina Fiterau. HyperFuse: Multimodal Fusion via Hypernetworks Submited to ICML, 2025. pdf.